How do I install the agenttrust mcp server?

This profile does not contain a verified copy-paste launch configuration. Follow the current project documentation to confirm the runtime, entry point, transport and authentication before registering it in your client.

What credentials does it need?

It reads `GROQ_API_KEY`, `CEREBRAS_API_KEY` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

AgentTrust MCP Server

Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

Local serverstdioPython

What is the AgentTrust MCP Server?

Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

What you get

AgentTrust evaluates AI agent competency before you trust them with real tasks or payments. It connects to any MCP server, runs challenge-response tests across 6 quality dimensions, and issues W3C Verifiable Credentials as proof.

What the assistant can call

Once AgentTrust is connected, these are the calls the assistant has available:

API — http://localhost:8002
Health — http://localhost:8002/health
Method — Endpoint
POST — /v1/evaluate
GET — /v1/evaluate/{id}

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Configuration

Variable	Description	Required
GROQ_API_KEY	Credential the server authenticates with.	Yes
CEREBRAS_API_KEY	Credential the server authenticates with.	Yes

Example prompts to try

“Use AgentTrust to API.”
“Use AgentTrust to Health.”
“Use AgentTrust to Method.”

Frequently asked questions

Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.